bupaR vs PM4Py

bupaR is a free, open-source suite of R packages for working with business process data. It supports importing and preparing event data, calculating descriptive statistics, visualising processes, and checking conformance. Analysts can examine control flow, performance, and organisational aspects, while including custom process attributes in their workflow. It handles event logs, where each row represents an event, and activity logs, where each row represents an activity instance. Process maps help summarise processes and can be used in Shiny apps or exported to PDF, PNG, PS, or EPS. The bupaverse core contains bupaR, edeaR, eventdataR, processcheckR, and processmapR. The xesreadR package reads XES files from a local path or URL and writes event logs to XES. Installation instructions cover CRAN and GitHub development versions. The package requires R 3.5.0 or later and is licensed under MIT plus a license file. For prediction with processpredictR, Python, TensorFlow, and Keras are required. Validation of larger event logs can take time, though the documentation allows it to be disabled when the data meets requirements.

PM4Py is a Python library for developers who want to run process mining algorithms in their own code. From event data, it can produce directly-follows graphs, Petri nets, BPMN models, and process trees. It also compares observed behavior with process models using replay and alignment-based measures. Its object-centric analysis handles event logs where events link multiple object types, such as orders, items, and deliveries. PM4Py imports and exports event logs and supports XES and OCEL 1.0 and 2.0. It can extract machine-learning features for use with pandas and scikit-learn. The free Community Version is under AGPL v3; covered work using PM4Py must be published under AGPL when distributed or made available over a network. A commercial license permits closed-source use, with pricing available by quote. Commercial evaluation without publishing code is available by requesting an evaluation license. PM4Py runs on Windows, Linux, and macOS, and pip is the recommended installation method. Graphviz must be installed and configured for visualization features.